Machine Learning Model for Screening Thyroid Stimulating Hormone Receptor Agonists Based on Updated Datasets and Improved Applicability Domain Metrics.

Machine learning (ML) models for screening endocrine-disrupting chemicals (EDCs), such as thyroid stimulating hormone receptor (TSHR) agonists, are essential for sound management of chemicals. Previous models for screening TSHR agonists were built on imbalanced datasets and lacked applicability domain (AD) characterization essential for regulatory application. Herein, an updated TSHR agonist dataset was built, for which the ratio of active to inactive compounds greatly increased to 1:2.6, and chemical spaces of structure-activity landscapes (SALs) were enhanced. Resulting models based on 7 molecular representations and 4 ML algorithms were proven to outperform previous ones. Weighted similarity density (ρs) and weighted inconsistency of activities (IA) were proposed to characterize the SALs, and a state-of-the-art AD characterization methodology ADSAL{ρs, IA} was established. An optimal classifier developed with PubChem fingerprints and the random forest algorithm, coupled with ADSAL{ρs ≥ 0.15, IA ≤ 0.65}, exhibited good performance on the validation set with the area under the receiver operating characteristic curve being 0.984 and balanced accuracy being 0.941 and identified 90 TSHR agonist classes that could not be found previously. The classifier together with the ADSAL{ρs, IA} may serve as efficient tools for screening EDCs, and the AD characterization methodology may be applied to other ML models.

Enhancement of Atmospheric Nucleation Precursors on Iodic Acid-Induced Nucleation: Predictive Model and Mechanism.

Iodic acid (IA) has recently been recognized as a key driver for new particle formation (NPF) in marine atmospheres. However, the knowledge of which atmospheric vapors can enhance IA-induced NPF remains limited. The unique halogen bond (XB)-forming capacity of IA makes it difficult to evaluate the enhancing potential (EP) of target compounds on IA-induced NPF based on widely studied sulfuric acid systems. Herein, we employed a three-step procedure to evaluate the EP of potential atmospheric nucleation precursors on IA-induced NPF. First, we evaluated the EP of 63 precursors by simulating the formation free energies (ΔG) of the IA-containing dimer clusters. Among all dimer clusters, 44 contained XBs, demonstrating that XBs are frequently formed. Based on the calculated ΔG values, a quantitative structure-activity relationship model was developed for evaluating the EP of other precursors. Second, amines and O/S-atom-containing acids were found to have high EP, with diethylamine (DEA) yielding the highest potential to enhance IA-induced nucleation by combining both the calculated ΔG and atmospheric concentration of considered 63 precursors. Finally, by studying larger (IA)1-3(DEA)1-3 clusters, we found that the IA-DEA system with merely 0.1 ppt (2.5×106 cm-3) DEA yields comparable nucleation rates to that of the IA-iodous acid system.

Zinc and selenium status in coronavirus disease 2019.

We systematically analyzed and attempted to discuss the possibility that deficiencies of zinc or selenium were associated with the incidence and severity of COVID-19. We searched for published and unpublished articles in PubMed, Embase, Web of Science and Cochrane up to 9 February 2023. And we selected healthy individuals, mild/severe, and even deceased COVID-19 patients to analyze their serum data. Data related to 2319 patients from 20 studies were analyzed. In the mild/severe group, zinc deficiency was associated with the degree of severe disease (SMD = 0.50, 95% CI 0.32-0.68, I2 = 50.5%) and we got an Egger's test of p = 0.784; but selenium deficiency was not associated with the degree of severe disease (SMD = - 0.03, 95% CI - 0.98-0.93, I2 = 96.7%). In the surviving/death group, zinc deficiency was not associated with mortality of COVID-19 (SMD = 1.66, 95%CI - 1.42-4.47), nor was selenium (SMD = - 0.16, 95%CI - 1.33-1.01). In the risk group, zinc deficiency was positively associated with the prevalence of COVID-19 (SMD = 1.21, 95% CI 0.96-1.46, I2 = 54.3%) and selenium deficiency was also positively associated with the prevalence of it (SMD = 1.16, 95% CI 0.71-1.61, I2 = 58.3%). Currently, serum zinc and selenium deficiencies increase the incidence of COVID-19 and zinc deficiency exacerbates the disease; however, neither zinc nor selenium was associated with mortality in patients with COVID-19. Nevertheless, our conclusions may change when new clinical studies are published.

Novel quantitative structure activity relationship models for predicting hexadecane/air partition coefficients of organic compounds.

Predicting the logarithm of hexadecane/air partition coefficient (L) for organic compounds is crucial for understanding the environmental behavior and fate of organic compounds and developing prediction models with polyparameter linear free energy relationships. Herein, two quantitative structure activity relationship (QSAR) models were developed with 1272 L values for the organic compounds by using multiple linear regression (MLR) and support vector machine (SVM) algorithms. On the basis of the OECD principles, the goodness of fit, robustness and predictive ability for the developed models were evaluated. The SVM model was first developed, and the predictive capability for the SVM model is slightly better than that for the MLR model. The applicability domain (AD) of these two models has been extended to include more kinds of emerging pollutants, i.e., oraganosilicon compounds. The developed QSAR models can be used for predicting L values of various organic compounds. The van der Waals interactions between the organic compound and the hexadecane have a significant effect on the L value of the compound. These in silico models developed in current study can provide an alternative to experimental method for high-throughput obtaining L values of organic compounds.

Biological Effects of Black Phosphorus Nanomaterials on Mammalian Cells and Animals.

The remarkable progress of applied black phosphorus nanomaterials (BPNMs) is attributed to BP's outstanding properties. Due to its potential for applications, environmental release and subsequent human exposure are virtually inevitable. Therefore, how BPNMs impact biological systems and human health needs to be considered. In this comprehensive Minireview, the most recent advancements in understanding the mechanisms and regulation factors of BPNMs' endogenous toxicity to mammalian systems are presented. These achievements lay the groundwork for an understanding of its biological effects, aimed towards establishing regulatory principles to minimize the adverse health impacts.

Prediction Models on pKa and Base-Catalyzed Hydrolysis Kinetics of Parabens: Experimental and Quantum Chemical Studies.

Parabens for which the molecules contain hydrolytic and ionizable groups, are emerging pollutants due to their ubiquity in the environment. However, lack of pKa and second-order base-catalyzed hydrolysis kinetics (kB) values limits their environmental persistence assessment. Herein, six parabens were selected as reference compounds for which the pKa and kB values were measured experimentally. A semiempirical quantum chemical (QC) method was selected to calculate pKa of the parabens, and density functional theory (DFT) methods were selected to calculate kB for neutral and anionic forms of the parabens, by comparing the QC-calculated and determined values. Combining the QC-calculated and experimental pKa and kB values, quantitative structure-activity relationships with determination coefficients (R2) being 0.947 and 0.842 for the pKa and kB models, respectively, were developed, which were validated and could be employed to efficiently fill the kB and pKa data gaps of parabens within applicability domains. The base-catalyzed hydrolysis half-lives were estimated to range from 6 h to 1.52 × 106 years (pH 7-9, 25 °C), further necessitating the in silico models due to the tedious and onerous experimental determination, and the huge number of hydrolyzable and ionizable chemicals that may be released into the environment.

Identification of prognosis-related alternative splicing events in kidney renal clear cell carcinoma.

Alternative splicing (AS) contributes to protein diversity by modifying most gene transcriptions. Cancer generation and progression are associated with specific splicing events. However, AS signature in kidney renal clear cell carcinoma (KIRC) remains unknown. In this study, genome-wide AS profiles were generated in 537 patients with KIRC in the cancer genome atlas. With a total of 42 522 mRNA AS events in 10 600 genes acquired, 8164 AS events were significantly associated with the survival of patients with KIRC. Logistic regression analysis of the least absolute shrinkage and selection operator was conducted to identify an optimized multivariate prognostic predicting mode containing four predictors. In this model, the receptor-operator characteristic curves of the training set were built, and the areas under the curves (AUCs) at different times were >0.88, thus indicating a stable and powerful ability in distinguishing patients' outcome. Similarly, the AUCs of the test set at different times were >0.73, verifying the results of the training set. Correlation and gene ontology analyses revealed some potential functions of prognostic AS events. This study provided an optimized survival-predicting model and promising data resources for future in-depth studies on AS mechanisms in KIRC.

Immune cell infiltration characteristics and related core genes in lupus nephritis: results from bioinformatic analysis.

BACKGROUND: Lupus nephritis (LN) is a common complication of systemic lupus erythematosus that presents a high risk of end-stage renal disease. In the present study, we used CIBERSORT and gene set enrichment analysis (GSEA) of gene expression profiles to identify immune cell infiltration characteristics and related core genes in LN. RESULTS: Datasets from the Gene Expression Omnibus, GSE32591 and GSE113342, were downloaded for further analysis. The GSE32591 dataset, which included 32 LN glomerular biopsy tissues and 14 glomerular tissues from living donors, was analyzed by CIBERSORT. Different immune cell types in LN were analyzed by the Limma software. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway analysis based on GSEA were performed by clusterProfiler software. Lists of core genes were derived from Spearman correlation between the most significant GO term and differentially expressed immune cell gene from CIBERSORT. GSE113342 was employed to validate the association between selected core genes and clinical manifestation. Five types of immune cells revealed important associations with LN, and monocytes emerged as having the most prominent differences. GO and KEGG analyses indicated that immune response pathways are significantly enriched in LN. The Spearman correlation indicated that 15 genes, including FCER1G, CLEC7A, MARCO, CLEC7A, PSMB9, and PSMB8, were closely related to clinical features. CONCLUSIONS: This study is the first to identify immune cell infiltration with microarray data of glomeruli in LN by using CIBERSORT analysis and provides novel evidence and clues for further research of the molecular mechanisms of LN.

Development of Prediction Models on Base-Catalyzed Hydrolysis Kinetics of Phthalate Esters with Density Functional Theory Calculation.

Many phthalate esters (PAEs) are chemicals of high production volume and of toxicological concern. The second-order rate constant for base-catalyzed hydrolysis ( kB) is a key parameter for assessing environmental persistence of PAEs. However, the kB values for most PAEs are lacking, and the experimental determination of kB encounters various difficulties. Herein, density functional theory (DFT) methods were selected by comparing empirical kB values of five PAEs and five carboxylic acid esters with the DFT-calculated ones. Results indicate that PAEs with cyclic side chains are more vulnerable to base-catalyzed hydrolysis than PAEs with linear alkyl side chains, followed by PAEs with branched alkyl side chains. By combining experimental and DFT-calculated second-order rate constants for base-catalyzed hydrolysis of one side chain in PAEs ( kB_side chain), quantitative structure-activity relationship models were developed. The models can differentiate PAEs with the departure of the leaving group (or the nucleophilic attack of OH-) as the rate-determining step in the hydrolysis and estimate kB values, which provides a promising way to predict hydrolysis kinetics of PAEs. The half-lives of the investigated PAEs were calculated and vary from 0.001 h to 558 years (pH = 7∼9), further illustrating the necessity of prediction models for hydrolysis kinetics in assessing the environmental persistence of chemicals.

Deep learning for predicting toxicity of chemicals: a mini review.

Humans and wildlife inhabit a world with panoply of natural and synthetic chemicals. Alarmingly, only a limited number of chemicals have undergone comprehensive toxicological evaluation due to limitations of traditional toxicity testing. High-throughput screening assays provide a higher-speed alternative for conventional toxicity testing. Advancement of high-throughput bioassay technology has greatly increased chemical toxicity data volumes in the past decade, pushing toxicology research into a "big data" era. However, traditional data analysis methods fail to effectively process large data volumes, presenting both a challenge and an opportunity for toxicologists. Deep learning, a machine learning method leveraging deep neural networks (DNNs), is a proven useful tool for building quantitative structure-activity relationship (QSAR) models for toxicity prediction utilizing these new large datasets. In this mini review, a brief technical background on DNNs is provided, and the current state of chemical toxicity prediction models built with DNNs is reviewed. In addition, relevant toxicity data sources are summarized, possible limitations are discussed, and perspectives on DNN utilization in chemical toxicity prediction are given.

Computational Nanotoxicology Models for Environmental Risk Assessment of Engineered Nanomaterials.

Although engineered nanomaterials (ENMs) have tremendous potential to generate technological benefits in numerous sectors, uncertainty on the risks of ENMs for human health and the environment may impede the advancement of novel materials. Traditionally, the risks of ENMs can be evaluated by experimental methods such as environmental field monitoring and animal-based toxicity testing. However, it is time-consuming, expensive, and impractical to evaluate the risk of the increasingly large number of ENMs with the experimental methods. On the contrary, with the advancement of artificial intelligence and machine learning, in silico methods have recently received more attention in the risk assessment of ENMs. This review discusses the key progress of computational nanotoxicology models for assessing the risks of ENMs, including material flow analysis models, multimedia environmental models, physiologically based toxicokinetics models, quantitative nanostructure-activity relationships, and meta-analysis. Several challenges are identified and a perspective is provided regarding how the challenges can be addressed.

Shared Transcriptomic Signatures of Inflammaging Among Diverse Strains of Drosophila melanogaster.

Background: A prominent hallmark of aging is inflammaging-the increased expression of innate immune genes without identifiable infection. Model organisms with shorter lifespans, such as the fruit fly, provide an essential platform for probing the mechanisms of inflammaging. Multiple groups have reported that, like mammalian models, old flies have significantly higher levels of expression of anti-microbial peptide genes. However, whether some of these genes-or any others-can serve as reliable markers for assessing and comparing inflammaging in different strains remains unclear. Methods and Results: We compared RNA-Seq datasets generated by different groups. Although the fly strains used in these studies differ significantly, we found that they share a core group of genes with strong aging-associated expression. In addition to anti-microbial peptide genes, we identified other genes that have prominently increased expression in old flies, especially SPH93. We further showed that machine learning models can be used to predict the "inflammatory age" of the fruit y. Conclusion: A core group of genes may serve as markers for studying inflammaging in Drosophila. RNA-Seq profiles, in combination with machine-learning models, can be applied to measure the acceleration or deceleration of inflammaging.

Handling the Challenges of Small-Scale Labeled Data and Class Imbalances in Classifying the N and K Statuses of Rubber Leaves Using Hyperspectroscopy Techniques.

The nutritional status of rubber trees (Hevea brasiliensis) is inseparable from the production of natural rubber. Nitrogen (N) and potassium (K) levels in rubber leaves are 2 crucial criteria that reflect the nutritional status of the rubber tree. Advanced hyperspectral technology can evaluate N and K statuses in leaves rapidly. However, high bias and uncertain results will be generated when using a small size and imbalance dataset to train a spectral estimaion model. A typical solution of laborious long-term nutrient stress and high-intensive data collection deviates from rapid and flexible advantages of hyperspectral tech. Therefore, a less intensive and streamlined method, remining information from hyperspectral image data, was assessed. From this new perspective, a semisupervised learning (SSL) method and resampling techniques were employed for generating pseudo-labeling data and class rebalancing. Subsequently, a 5-classification spectral model of the N and K statuses of rubber leaves was established. The SSL model based on random forest classifiers and mean sampling techniques yielded optimal classification results both on imbalance/balance dataset (weighted average precision 67.8/78.6%, macro averaged precision 61.2/74.4%, and weighted recall 65.7/78.5% for the N status). All data and code could be viewed on the:Github https://github.com/WeehowTang/SSL-rebalancingtest. Ultimately, we proposed an efficient way to rapidly and accurately monitor the N and K levels in rubber leaves, especially in the scenario of small annotation and imbalance categories ratios.

Composition and release rates of chemicals in inkjet fabrics determined by non-targeted screening and targeted analysis.

Unveiling composition and release rates of chemicals in chemical-intensive products (CIPs) such as inkjet fabrics that are applied extensively in advertising and publicizing industries, is of importance to sound management of chemicals. This study tentatively identified 212 compounds from 69 inkjet fabric samples using gas chromatograph coupled with quadrupole time-of-flight mass spectrometry (GC-QTOF-MS). Contents of six phthalate esters (PAEs) were quantified to range from 3.0 × 102 mg/kg to 3.1 × 105 mg/kg with GC-MS. Bis(2-ethylhexyl) phthalate was predominantly detected to average 96 g/kg. The inkjet fabrics collected from southern China contained fewer non-intentionally added substances (NIASs) than from northern China. Annual mass release rates (RM) of the 6 PAEs from inkjet fabrics to air were estimated to range from 1.4 × 10-2 kg/year to 2.8 × 104 kg/year in China in 2020, and the mean indoor RM was comparable with the outdoor one. Equilibrium partition coefficients of the compounds between the product and air, ambient temperature, and concentrations of chemicals in the product, are key factors leading to RM with the high variance. The findings indicate that contents of the NIASs in the CIPs should be minimized, and the refining concept should be adopted in design of the CIPs, so as to control the release of chemicals from the CIPs.

Estimation of reduced greenhouse gas emission from municipal solid waste incineration with electricity recovery in prefecture- and county-level cities of China.

Municipal solid waste (MSW) without proper managements could be a significant source of greenhouse gas (GHG) emissions. MSW incineration with electricity recovery (MSW-IER) is recognized as a sustainable way to utilize waste, but its effectiveness on reducing GHG emissions at the city scale in China remain unclear due to limited data of MSW compositions. The aim of the study is to investigate reduction potential of GHG from MSW-IER in China. Based on the MSW compositions covering 106 Chinese prefecture-level cities during the period of 1985 to 2016, random forest models were built to predict MSW compositions in Chinese cities. MSW compositions in 297 cities of China from 2002 to 2017 were predicted using the model trained by a combination of socio-economic, climate and spatiotemporal factors. Spatiotemporal and climatic factors (such as economic development level, precipitation) accounted for 6.5 %-20.7 % and 20.1 %-37.6 % to total contributions on MSW composition, respectively. The GHG emissions from MSW-IER in each Chinese city were further calculated based on the predicted MSW compositions. The plastic is the main GHG emission source, accounting for over 91 % of the total emission during 2002-2017. Compared to baseline (landfill) emission, the GHG emission reduction from MSW-IER was 12.5 × 107 kg CO2-eq in 2002 and 415 × 107 kg CO2-eq in 2017, with an average annual growth rate of 26.3 %. The results provide basic data for estimating GHG emission in MSW management in China.

Machine learning models on chemical inhibitors of mitochondrial electron transport chain.

Chemicals can induce adverse effects in humans by inhibiting mitochondrial electron transport chain (ETC) such as disrupting mitochondrial membrane potential, enhancing oxidative stress and causing some diseases. Thus, identifying ETC inhibitors (ETCi) is important to chemical risk assessment and protecting the public health. However, it is not feasible to identify all ETCi with experimental methods. Quantitative structure-activity relationship (QSAR) modeling is a promising method to rapidly and effectively identify ETCi. In this study, QSAR models for predicting ETCi were developed using machine learning methods. A clustering-based under-sampling (CBUS) method was developed to handle the imbalance issue in training sets. Structure-activity landscapes were generated and analyzed for training sets generated by the CBUS method. The consensus QSAR models constructed with CBUS achieved satisfactory performances (balanced accuracy = 0.852) in 100 iterations of five-fold cross validations, indicating the models can effectively classify ETCi. The classification model was further employed to screen chemicals in the Inventory of Existing Chemical Substances of China and 13 chemicals were identified as ETCi. Fifteen structural alerts for ETCi were identified in this study. These results demonstrated that the model and structural alerts are useful to screen ETCi.

Prediction models on biomass and yield of rice affected by metal (oxide) nanoparticles using nano-specific descriptors.

The use of in silico tools to investigate the interactions between metal (oxide) nanoparticles (NPs) and plant biological responses is preferred because it allows us to understand molecular mechanisms and improve prediction efficiency by saving time, labor, and cost. In this study, four models (C5.0 decision tree, discriminant function analysis, random forest, and stepwise multiple linear regression analysis) were applied to predict the effect of NPs on rice biomass and yield. Nano-specific descriptors (size-dependent molecular descriptors and image-based descriptors) were introduced to estimate the behavior of NPs in plants to appropriately represent the wide space of NPs. The results showed that size-dependent molecular descriptors (e.g., E-state and connectivity indices) and image-based descriptors (e.g., extension, area, and minimum ferret diameter) were associated with the behavior of NPs in rice. The performance of the constructed models was within acceptable ranges (correlation coefficient ranged from 0.752 to 0.847 for biomass and from 0.803 to 0.905 for yield, while the accuracy ranged from 64% to 77% for biomass and 81% to 89% for yield). The developed model can be used to quickly and efficiently evaluate the impact of NPs under a wide range of experimental conditions and sufficient training data.

[Dynamic Material Flow Analysis of Perfluorooctane Sulfonate in China: 1985-2019].

Perfluorooctane sulfonates (PFOS) are regarded as a category of chemicals with persistence, bioaccumulation, and toxicity. Understanding dynamic flows, stocks, and emissions of PFOS on a macro spatial and temporal scale can help provide a scientific basis for their sound management. In this work, a dynamic material flow analysis (d-MFA) model was built to characterize and analyze the cycles of PFOS in mainland China over the period 1985-2019. Flows, stocks, and environmental emissions were calculated and the sensitivity and uncertainty of the results were then analyzed. Results show that domestic production was the primary source of PFOS in China, most of which was flowed to the domestic market in the form of final products, with the remainder exported to international markets; soil and water were the main sinks of PFOS in China, with emissions from the usage stage contributing the largest portion (103 tons in 2019). The number of inflows and outflows were relatively low before 2000, but gradually increased until 2009 when the relevant convention was issued. Since 2005, in-use stocks and emissions of PFOS have grown yearly. In addition, stocks in landfill have been climbing since 1985. End-of-life management was still dominated by traditional methods, such as landfill and incineration, while there was a trend towards green treatments. This study can provide basic data and theoretical support for the sound management of PFOS in China.

The Possible Transmission and Potential Enterotoxicity of Bacillus cereus on Lettuce Farms in Five Chinese Provinces.

Bacillus cereus is a well-characterized human pathogen that produces toxins associated with diarrheal and emetic foodborne diseases. To investigate the possible transmission of B. cereus on lettuce farms in China and determine its enterotoxicity, (I) a total of 524 samples (lettuce: 332, soil: 69, water: 57, manure: 57, pesticide: 9) were collected from 46 lettuce farms in five Chinese provinces, (II) multilocus sequence typing (MLST) was used to classify B. cereus isolates and for trace analysis, and (III) the presence of toxin genes and enterotoxins (Hbl and Nhe) was detected in 68 strains. The results showed that one hundred and sixty-one lettuce samples (48.5%) tested positive for B. cereus at levels ranging from 10 to 5.3 × 104 CFU/g. Among the environmental sample categories surveyed, the highest positive rate was that of the pesticide samples at 55.6%, followed by soil samples at 52.2% and manure samples at 12.3%. Moreover, one hundred isolates of B. cereus yielded 68 different sequence types (STs) and were classified into five phylogenetic clades. Furthermore, Nhe toxin genes (nheA, nheB, nheC) were broadly distributed and identified in all 68 strains (100%), while Hbl toxin genes (hblA, hblC, hblD) were present in 61 strains (89.7%), entFM was detected in 62 strains (91.2%), and cytK was found in 29 strains (42.6%). All strains were negative for ces. As for the enterotoxin, Nhe was observed in all 68 isolates carrying nheB, while Hbl was present in 76.5% (52/68) of the strains harboring hblC. This study is the first report of possible B. cereus transmission and of its potential enterotoxicity on lettuce farms in China. The results showed that soil and pesticides are the main sources of B. cereus on lettuce farms in China, and the possible transmission routes are as follows: soil-lettuce, manure-lettuce, pesticide-lettuce, manure-soil-lettuce, and water-manure-soil-lettuce. Furthermore, the B. cereus isolates, whether from lettuce or the environment, pose a potential risk to health.

Development of classification models for predicting inhibition of mitochondrial fusion and fission using machine learning methods.

Mitochondrial fusion and fission are processes to maintain mitochondrial function when cells respond to environment stresses. Disruption of mitochondrial fusion and fission influences cell health and can cause adverse events such as neurodegenerative disorders. It is critical to identify environmental chemicals that can disrupt mitochondrial fusion and fission. However, experimentally testing all the chemicals is not practical because experimental methods are time-consuming and costly. Quantitative structure-activity relationship (QSAR) modeling is an attractive approach for evaluation of chemicals disrupting potential on mitochondrial fusion and fission. In this study, QSAR models were developed for differentiating chemicals capable of inhibition of mitochondrial fusion and fission using machine learning algorithms (i.e. random forest, logistic regression, Bernoulli naive Bayes, and deep neural network). One hundred iterations of five-fold cross validations and external validations showed that the best model on mitochondrial fusion had area under the receiver operating characteristic curve (AUC) of 82.8% and 78.1%, respectively; and the best model for mitochondrial fission yielded AUC of 84.3% and 97.5%, respectively. Furthermore, 45 and 56 structural alerts were identified for inhibition of mitochondrial fusion and fission, respectively. The results demonstrated that the models and the structural alerts could be useful for screening chemicals that inhibit mitochondrial fusion and fission.